{ "openapi": "3.0.1", "info": { "title": "Website Images Scraper", "description": "Website Images Scraper SD - Website Images Scraper is a no-login tool that extracts every image from any website (img, srcset, picture, lazy data-src, CSS backgrounds, og:image) with alt text, size, type and dimensions, crawls pages, filters, and downloads files to storage or a ZIP.", "version": "1.0", "x-build-id": "tBLHzcYEkyizOacoP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~website-images-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-website-images-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~website-images-scraper/runs": { "post": { "operationId": "runs-sync-neuro-scraper-website-images-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~website-images-scraper/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-website-images-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "startUrls": { "title": "Website or page URLs", "type": "array", "description": "Pages to collect images from, e.g. https://books.toscrape.com/ . Each page's images are read, then (Crawl scope, Maximum crawl depth) its links are followed page by page. A link straight to an image file (…/photo.jpg) is read as one image. The names urls and startUrl are accepted too.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "imageUrls": { "title": "Image file URLs (bulk download)", "type": "array", "description": "Optional. Direct links to image (or video / audio) files, one per line, e.g. https://upload.wikimedia.org/wikipedia/commons/a/a7/Camponotus_flavomarginatus_ant.jpg . Each gives one row with type, size and dimensions; turn on Download images to store the files.", "items": { "type": "string" } }, "mode": { "title": "URL mode", "enum": [ "auto", "page", "direct" ], "type": "string", "description": "auto = a start URL ending in an image / video / audio extension (or answering with an image) is read as a file, every other one as a page. page = always parse as a web page. direct = every start URL is an image file.", "default": "auto" }, "crawlScope": { "title": "Crawl scope", "enum": [ "single-page", "same-domain", "include-subdomains" ], "type": "string", "description": "Which links are followed from the start page: only the start page, pages on the same domain (www. ignored), or the domain and its subdomains. Allowed page URL globs replace this when given.", "default": "same-domain" }, "maxCrawlDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many links away from a start URL pages are read: 0 = the start page only, 1 = the start page and the pages it links to, 2 = one level further. crawlDepth is accepted as the same setting.", "default": 1 }, "maxPagesToCrawl": { "title": "Max pages to crawl", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Most pages read in the whole run (start pages included), breadth-first. The crawl also stops when Max images is reached or no page is left to read. maxPages is accepted as the same setting.", "default": 10 }, "urlGlobs": { "title": "Allowed page URL globs", "type": "array", "description": "Optional. Only follow links matching one of these globs (** = anything, * = anything except /), e.g. https://books.toscrape.com/catalogue/page-*.html . Replaces Crawl scope when set.", "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Excluded page URL globs", "type": "array", "description": "Optional. Never follow links matching these globs, e.g. **/login** or **/cart/**.", "items": { "type": "string" } }, "maxItems": { "title": "Max images", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Most image rows in the whole run (every row is one result). The crawl follows the site's links page by page until this number, Max pages to crawl or the end of the site. maxTotalImages is accepted as the same setting.", "default": 100 }, "maxImagesPerPage": { "title": "Max images per page", "minimum": 0, "type": "integer", "description": "Most images saved from one page (0 = no limit).", "default": 0 }, "maxImagesPerUrl": { "title": "Max images per start URL", "minimum": 0, "type": "integer", "description": "Most images saved for one start URL and the pages crawled from it (0 = no limit).", "default": 0 }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Collect images (img tags and every source below). Turn off to collect only video / audio.", "default": true }, "includeSrcset": { "title": "Include srcset / picture", "type": "boolean", "description": "Read responsive images: srcset, data-srcset and . The largest candidate is returned (see Merge resized copies).", "default": true }, "includeBackgroundImages": { "title": "Include CSS background images", "type": "boolean", "description": "Images set with CSS: style=\"background-image:url(...)\",